Leveraging billions of data items and machine learning to map the future
With over one billion total listings on the Mercari app to date and with the remarkable advancements observed in recent years in the fields of machine learning and deep learning, there is increasingly greater focus on, and expectations for, data utility. There are a number of projects underway which utilize data on items and user behavior, and several features, including image recognition for listings and automatic detection of fraudulent listings, are already in operation on the service. This session will introduce those algorithms and execution platforms and will also introduce a number of features currently in development.
Software Engineer (Machine Learning)
Takuma Yamaguchi has been involved in research on pattern recognition and machine learning since he was a student and has a PhD in engineering. In addition to his research on image recognition, computer vision, and voice recognition, he has also led a research project on algorithms for the calculation of train fares using operations research. After working at a company that developed social games, where he was responsible for the development and operation of their data analysis platform, he joined Mercari in 2016. At Mercari, he is responsible for image-focused machine learning, and has developed an image recognition feature that can be used when listing items on the app.